Logical Reasoning on RepublicQA
87AccuracyLogicAgent
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| LogicAgentType=AR+SR, Base Model=GPT-4o2025.09 | 87 | — | |
| AristotleType=AR+SR, Base Model=GPT-4o2025.09 | 82.5 | — | |
| LogicAgentType=AR+SR, Base Model=Qwen2.52025.09 | 82.5 | — | |
| SymbCoTType=SR, Base Model=GPT-4o2025.09 | 80.5 | — | |
| SymbCoTType=SR, Base Model=Qwen2.52025.09 | 76 | — | |
| CoTType=LR, Base Model=GPT-4o2025.09 | 75 | — | |
| AristotleType=AR+SR, Base Model=Qwen2.52025.09 | 74.5 | — | |
| NaiveType=LR, Base Model=GPT-4o2025.09 | 74 | — | |
| Logic-LMType=SR, Base Model=GPT-4o2025.09 | 73.5 | — | |
| CoTType=LR, Base Model=Qwen2.52025.09 | 72 | — | |
| CRType=AR, Base Model=GPT-4o2025.09 | 71 | — | |
| Logic-LMType=SR, Base Model=Qwen2.52025.09 | 70 | — | |
| ToTType=AR, Base Model=GPT-4o2025.09 | 69.5 | — | |
| NaiveType=LR, Base Model=Qwen2.52025.09 | 68.5 | — | |
| CRType=AR, Base Model=Qwen2.52025.09 | 57 | — | |
| ToTType=AR, Base Model=Qwen2.52025.09 | 56 | — | |
| AristotleType=AR+SR, Base Model=Aggregate2025.09 | — | 78.5 | |
| CoTType=LR, Base Model=Aggregate2025.09 | — | 73.5 | |
| CRType=AR, Base Model=Aggregate2025.09 | — | 64 | |
| Logic-LMType=SR, Base Model=Aggregate2025.09 | — | 71.75 | |
| LogicAgentType=AR+SR, Base Model=Aggregate2025.09 | — | 84.75 | |
| NaiveType=LR, Base Model=Aggregate2025.09 | — | 71.25 | |
| SymbCoTType=SR, Base Model=Aggregate2025.09 | — | 78.25 | |
| ToTType=AR, Base Model=Aggregate2025.09 | — | 62.75 |